Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 6013 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2407. Min Act: -0.0001

Data Index: 19695 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1104632 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2211. Min Act: -0.0001

Data Index: 1001986 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2112. Min Act: -0.0001

Data Index: 317526 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2104. Min Act: -0.0001

Data Index: 519220 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2038. Min Act: -0.0001

Data Index: 287769 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2035. Min Act: -0.0001

Data Index: 1058825 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2050. Min Act: -0.0001

Data Index: 1342992 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1989. Min Act: -0.0001

Data Index: 964674 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2005. Min Act: -0.0001

Data Index: 235410 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1989. Min Act: -0.0001

Data Index: 1194779 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2035. Min Act: -0.0001

Data Index: 466395 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2015. Min Act: -0.0001

Data Index: 90429 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2029. Min Act: -0.0001

Data Index: 6989 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2020. Min Act: -0.0001

Data Index: 1036065 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1983. Min Act: -0.0001

Data Index: 112042 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1964. Min Act: -0.0001

Data Index: 533469 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1928. Min Act: -0.0001

Data Index: 25105 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1971. Min Act: -0.0001

Data Index: 705337 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1956. Min Act: -0.0001

Data Index: 546268 (C4 (Web Text))

Max Activating Token Index: 166